Electroencephalogram (EEG)-based fatigue recognition using deep learning techniques

• Main Author: Cheng, Zhiao
• Other Authors: Wang Lipo
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/149462
• Institution: Nanyang Technological University

Fatigue driving is a growing hot issue that captures our eyes which results in more and more vehicle accidents threatening our safety. Electroencephalography (EEG) is the record of neurophysiological activities in human brain and is considered as one of the most popular ways of detecting drivers’ fatigue levels. In this paper, we proposed a compact Convolutional Neural Network (CNN) model to achieve high accuracy results and use visualization tool to discover cross-subject EEG features. From the results, we achieve a good performance of 73.75% mean accuracy which is higher than other conventional baseline methods.